26 results about "Restrict boltzmann machine" patented technology

The invention discloses a networking charging data cross-platform fusion and transmission method based on an intelligent scheduling algorithm. The method comprises the following steps: S1, collecting and preprocessing networking platform charging data; s2, feature similarity is calculated, and an undirected graph with samples as nodes and similarity as edge weight is constructed; s3, calculating a standardized Laplacian matrix, extracting feature vectors, and clustering to generate feature cluster tags; s4, constructing a modal mapping matrix, mapping the feature vectors, and inputting the mapped feature vectors into a first convolution restricted Boltzmann machine to extract fusion features; s5, inputting the fusion features into a second convolution restricted Boltzmann machine, and combining graph structure sorting and constructing a weighted directed graph; s6, initializing a virtual scheduling factor in the graph, and searching an optimal transmission path by an ant colony algorithm; and S7, distributing fusion features according to paths, and realizing cross-platform efficient transmission of charging data. According to the method, spectral clustering, modal mapping, convolution extraction and intelligent scheduling are fused, and the multi-platform charging data fusion accuracy and transmission efficiency are improved.

The present invention relates to a method for diagnosing and predicting the course of Alzheimer's disease (AD)-related dementia after feature extraction of brain images by Variational Autoencoders (VAE) and using Artificial intelligence and Machine learning (AI / ML) algorithms, as compared with non-demented control cases (CN), mild cognitive impairment (MCI), and other non-Alzheimer's dementia (non-ADD) cases. Method 1 extracts the reduced dimensional latent feature vector from the sMRI scans / brain images using a VAE and does multiple sampling from the latent distribution to reduce the class imbalance followed by classification using different AI / ML models. Method 2, the extracted feature vectors from VAE are used as input to a mixture of class-Restricted Boltzmann Machines (cl-RBM) for AD, MCI, and CN classification. Method-1 diagnoses AD and distinguishes it from MCI, CN, and non-ADD using MRI scans with or without additional aids. Method-2 further extends to diagnosis and prediction of AD.

The invention discloses a distributed photovoltaic power prediction method and system, belongs to the technical field of renewable energy prediction, and solves the prediction precision and efficiency bottlenecks of a traditional model under complex meteorological conditions through fusion of deep feature learning and an adaptive optimization mechanism. Firstly, a time sequence sample set is constructed based on a sliding window mechanism, and non-stationary fluctuation characteristics of a power sequence are dynamically captured; eliminating the dimensional difference between the input features and the tags through minimum-maximum normalization; constructing a four-level restricted Boltzmann machine stacking structure, and extracting time-space coupling characteristics of power data by layer-by-layer unsupervised pre-training; and designing an improved extreme learning machine dynamic analysis architecture, optimizing the number of neurons in a hidden layer in combination with grid search, and realizing global optimal balance between model complexity and prediction precision. According to the method, an effective dynamic mode and noise interference are distinguished by using hierarchical feature abstraction capability of the RBM, prediction robustness in strong fluctuation scenes such as cloudy and rainy scenes is remarkably improved through analytical solution and parameter adaptive adjustment of the ELM, and efficient technical support is provided for intelligent scheduling and energy storage optimization in a high-proportion photovoltaic grid-connected background.

The invention relates to a cross-modal medical data hash retrieval method assisted by a large language model, and belongs to the field of artificial intelligence information retrieval in an intelligent medical system. Designing an image description type prompt template, a diagnosis report summary type prompt template and a combined modal reasoning type prompt template in combination with the semantic generalization ability of the large language model to perform modal data enhancement, and realizing deep semantic mining of medical image and diagnosis report data; a structured coding layer is utilized to ensure that the features of the image and the text can be accurately matched in a unified embedding space; finely adjusting the large language model by adopting a mode of combining soft prompt and hard prompt to realize alignment of image and text features; a Gaussian binary restricted Boltzmann machine is introduced to carry out probabilistic Hash mapping, data structure information is effectively reserved, and Hash codes are generated to carry out cross-modal Hash retrieval. Semantic similarity retrieval of medical cases among different modes can be realized, high retrieval efficiency is realized, and accurate and personalized diagnosis and treatment schemes are provided for patients.

The invention discloses a method for optically realizing a restricted Boltzmann machine. According to the invention, analog calculation of the restricted Boltzmann machine and optical Gibbs sampling can be realized, and the system has the advantages of wide application range, fast information transmission, simple structure, low cost, fast calculation and the like. According to the invention, a coherent wide-spectrum light source is used as signal input, a light field is subjected to light splitting by using a light splitting device such as a grating and then enters a modulator, then spinning, interaction and magnetic field parameters are coded on light wavefront at different positions through a time or space light modulator, and optical Fourier transform is carried out by using a time or space lens system, so that the optical field is obtained. The light intensity after Fourier transform is measured through the detector, and finally the difference between the light intensity measured twice is calculated, so that optical Gibbs sampling is realized, the calculation complexity is reduced, and the calculation efficiency is improved. The method provided by the invention has important application prospects in the fields of optical neural networks and the like, can realize applications of content generation, classification and identification and the like, and is convenient to integrate in optical chips and the like.

The invention discloses a coal mine catastrophe scene deduction method, which belongs to mine disaster emergency rescue, and comprises the following steps: collecting environmental data of a coal mine stope; performing data screening according to the environment data and the key elements, and extracting time sequence features; deducing time sequence characteristics by using an energy-based dynamic time sequence model to obtain probability energy distribution of disaster development; according to the probability energy distribution, constructing a Boltzmann machine model with a limited time sequence for predicting a mine catastrophe development trend; wherein the explicit layer unit corresponds to a sensor observation value at a current time point, the hidden layer unit captures potential time sequence characteristics and modes, correlation between a hidden layer at the current moment and hidden layers at the previous N moments is established through time sequence connection, and model training is conducted through a time-dependent conditional contrast divergence algorithm; aiming at the problem that a traditional Boltzmann machine model is mainly used for processing static distribution, so that the processing precision of a coal mine catastrophe scene with obvious time sequence evolution characteristics is low, the coal mine catastrophe scene deduction precision is improved.

The invention provides a flower quality grading quality inspection method and system based on AI and image processing, and belongs to the technical field of computer vision and pattern recognizing.The method comprises the steps that an original image of the surface of a flower is collected through high-resolution imaging equipment, and high-frequency sub-band data representing tiny physical characteristics are extracted through multistage discrete wavelet transform; meanwhile, a sliding window is adopted to traverse the image, the color information entropy of a local area is calculated, and a color entropy graph is constructed. And after vectoring and splicing the two types of features, inputting the two types of features into a deep belief network model based on a multilayer restricted Boltzmann machine, and extracting deep abnormal feature codes. And finally, performing linear discriminant analysis on the code by utilizing a classification projection vector based on inter-class and intra-class distance optimization to generate an insect attack infection index, and realizing automatic grading quality inspection of the flower quality according to the insect attack infection index. According to the method, precise recognition and quantitative grading of tiny insect pests and recessive lesions on the surfaces of the fresh flowers are realized.

Embodiments of the present disclosure relate to a question answering method, an electronic device, and a computer program product. The method includes: determining an answer library associated with a question; determining a restricted Boltzmann machine associated with the answer library, wherein the restricted Boltzmann machine is configured to determine a set of questions that the answer library can answer and association relationships between questions in the set of questions and the answer library; and determining, using the restricted Boltzmann machine, annotation information associated with the question and targeted to the answer library. With the technical solution of the present disclosure, it is possible to determine, while determining an answer library associated with the question, annotation information that is targeted to the answer library, and to enable customer service personnel to have a more thorough understanding of the determined answer library and obtain targeted recommendation information.

The invention discloses a DBN neural network-based grid-connected circulating current resonance suppression method and system for a network construction type converter, and aims to solve the circulating current resonance problem of a grid-connected converter. According to the method, through a DBN neural network formed by stacking multiple layers of restricted Boltzmann machines, the output current of a converter and the voltage of a common connection point are subjected to preprocessing and feature extraction, and the frequency and amplitude of circulation resonance are accurately detected; on the basis of traditional voltage and current double closed-loop control, a compensation item dynamically associated with a DBN neural network detection result is introduced, a compensation function is optimized in real time through an adaptive weight adjustment mechanism, and precise suppression of circulation resonance is achieved. According to the invention, the detection precision and suppression efficiency of the ring current resonance are improved, the power loss is effectively reduced, and the robustness and the electric energy quality of the network-forming converter in a complex power grid environment are enhanced.

The present invention discloses a method, device and equipment for predicting drug side effects based on a restricted Boltzmann machine with a penalty regular term, including: constructing a target drug similarity matrix, a target side effect similarity matrix and a drug-side effect association matrix; constructing a drug restricted Boltzmann machine model and a side effect restricted Boltzmann machine model; constructing a maximum likelihood function based on initial model parameters, the target drug similarity matrix, the target side effect similarity matrix and the drug-side effect association matrix, adding a penalty term to the maximum likelihood function, and performing iterative training until a preset number of iterations is reached to obtain the optimal model parameters; finally, using the trained model to perform prediction. The present invention trains the optimal parameters of the model through the gradient descent algorithm of the maximum likelihood function with a penalty term, avoids overfitting during the training process, improves the prediction accuracy of the model, and makes the prediction results more accurate.

The invention discloses an environmental air quality monitoring method based on artificial intelligence. The method comprises the following steps: S1, collecting and processing air pollutant concentration data, meteorological parameter data and spatial geographic information data; s2, constructing an improved deep belief network model, wherein the improved deep belief network model comprises an input layer, a multi-layer restricted Boltzmann machine hidden layer, a multi-layer physical prior embedding layer, a space-time dependent modeling module and an output layer; s3, performing layer-by-layer unsupervised pre-training operation on the improved deep belief network model; s4, performing global fine tuning optimization on the improved deep belief network model; s5, performing adaptive dynamic adjustment on the weight of the physical consistency error term; s6, inputting monitoring data collected in real time into the improved deep belief network model after global fine tuning optimization, and executing forward reasoning operation; and S7, executing abnormal pollution event detection. According to the invention, the improved deep belief network model is adopted, and accurate prediction and intelligent early warning of the ambient air quality are realized.

Embodiments of the present disclosure relate to a question and answer method, an electronic device and a computer program product. The method comprises: determining an answer base associated with a question; determining a restricted Boltzmann machine associated with the answer base, the restricted Boltzmann machine being used to determine a question set that the answer base can answer and a relationship between a question in the question set and the answer base; and determining, using the restricted Boltzmann machine, description information associated with the question for the answer base. Using the technical solution of the present disclosure, the description information for the answer base can be determined at the same time as the answer base associated with the question is determined, and the customer service personnel can be made to have a more thorough understanding of the determined answer base and obtain targeted recommendation information by providing the determined description information to the customer service personnel, thereby improving the user experience of the customer service personnel using the question and answer system.

A first computing node of a system can receive sensor data about a physical environment. The first computing node can analyze the sensor data with a restricted Boltzmann machine (RBM) neural network to determine whether there is a fault condition in the physical environment, an identification of the fault condition being omitted from data used to train the RBM neural network. The first computing node can update the RBM neural network based on the sensor data to produce a first updated RBM neural network. The first computing node can send a first patch indicative of the first updated RBM neural network to a central server. The first computing node can receive, from the central server, information indicative of a second updated RBM neural network, the second updated RBM neural network being based on an aggregation of the first patch and of a second patch generated by a second computing node.

The present invention proposes a method and system for online drilling speed prediction during the drilling process based on multi-source information fusion. The method comprises: a drilling data preprocessing stage, in which drilling pressure, rotational speed, and torque are filtered; a drilling speed modeling optimization stage, in which a hybrid bat algorithm is used to improve the model structure of a restricted Boltzmann machine and a back-propagation neural network, forming a novel hybrid bat algorithm optimization-restricted Boltzmann machine-back-propagation neural network, and using this algorithm to establish an offline drilling speed prediction model for complex formation environments; and a drilling speed prediction model update stage, in which lithologic changes and time intervals are used as update conditions, and a sliding window strategy is used based on the fusion of multi-source formation and drilling information to update the drilling speed prediction model, thereby achieving online drilling speed prediction. The present invention has the beneficial effects of helping to shorten the drilling cycle, reduce operating costs, achieve high-precision drilling speed prediction, and is effective, laying an important foundation for intelligent optimization and control of the drilling process.

The invention discloses a precision machining process optimization method for a machine tool spindle system, and relates to the technical field of machining. Comprising the steps that multi-dimensional dynamic data of the whole machining process of a machine tool spindle system are obtained, and the multi-dimensional dynamic data comprise the spindle real-time rotating speed, the cutting feeding speed, the cutting depth, the spindle radial force, the axial force, the torque, spindle box temperature field distribution, the spindle vibration frequency and the tool rear tool face abrasion width. According to the method, time-space synchronization of multi-source data is realized by adopting a timestamp alignment algorithm, feature enhancement is performed through a high-dimensional feature matrix, data time deviation and redundant information are effectively eliminated, the pertinence and precision of feature extraction are improved, and meanwhile, a deep belief network model of an attention mechanism is fused, so that the accuracy of feature extraction is improved. Through a three-layer restricted Boltzmann machine structure and contrast divergence algorithm training, key processing features can be adaptively focused.

The invention discloses an emotion recognition method and device fusing multi-modal features, equipment and a medium, and relates to the field of emotion recognition. The method comprises the following steps: acquiring multi-modal data induced by a target emotion; the multi-modal data comprises a voice signal, a pronunciation signal and a glottis signal; multi-resolution Mel spectrogram depth feature extraction is carried out on the voice signals, and spectrogram depth features are obtained; performing phase-space reconstruction on the pronunciation signal, and extracting calculus features from a three-dimensional sample space obtained by phase-space reconstruction to obtain pronunciation features; extracting glottis features of the glottis signals; a hierarchical restricted Boltzmann machine is adopted to fuse the speech spectrogram depth feature, the pronunciation feature and the glottis feature to obtain a fused multi-modal feature, and then an improved stacked long and short term memory network is adopted to perform emotion recognition to obtain the emotion of a target. According to the invention, the accuracy of emotion recognition can be improved.

The invention discloses an image recognition and classification method for an interval type-2 fuzzy restricted Boltzmann machine, and the method comprises the steps: carrying out the preprocessing of collected image data, and forming a training set and a test set; constructing a fuzzy free energy function by adopting a symmetric triangular fuzzy number, an asymmetric triangular fuzzy number or a Gaussian fuzzy number, and obtaining a deblurred free energy function through defuzzification processing of a clear probability mean value; performing parameter updating by adopting a contrast divergence algorithm; and testing the model by using a test set, evaluating the robustness of the model on salt-containing and pepper noise, Gaussian noise and Poisson noise data by taking a reconstruction error as an index, and evaluating the image classification performance of the model through classification accuracy, mean value and standard deviation. According to the invention, the method achieves the recognition and classification of the displayed complex image, and also has good robustness when facing a variety of noise data.

The specification of the present disclosure relates to a device, method, and computer program for searching for genes in a synthetic lethality relationship by using a Gaussian restricted Boltzmann machine. According to any one of the above-described means for solving the problem, a gene in a synthetic lethality relationship with a target gene may be output through an artificial intelligence model trained by receiving a training data set including an mRNA expression value in RNA Seq data, the presence or absence of a mutation in WES data, and a dependency score in CRISPR KO data. In addition, it is possible to increase the efficiency of anticancer treatment by using the genes in a synthetic lethality relationship calculated by using the trained artificial intelligence model. In addition, it is possible to present a treatment route with low drug resistance by using the genes in a synthetic lethality relationship calculated by using the trained artificial intelligence model.

The present disclosure provides a bearing fault feature extraction method, which introduces a Gauss-Bernoulli restricted Boltzmann machine model, solves the problem that the input vector of the traditional restricted Boltzmann machine is restricted by the Bernoulli binary distribution and has poor reconstruction and fitting effect for non-binomial distributed data; uses the cosine loss function as the loss function, retains the advantage of the Softmax loss function in expanding the inter-class difference, and reduces the sensitivity to different signal strengths; combines the attention mechanism adaptively to more effectively extract features that are effective in describing the bearing status.

The invention relates to the technical field of computer data processing and artificial intelligence, and discloses a multi-type variable adaptive CRBM digital twinning modeling method, device and medium, the method comprises the following steps: obtaining modeling data and defining the modeling data as visible, conditional and hidden variable sets, the visible variables comprising non-standard distribution types; constructing a condition-restricted Boltzmann machine model, and directly constructing corresponding conditional probability distribution and interaction energy items according to original probability distribution characteristics for visible variables of non-standard distribution types; performing parameter updating on the model by calculating a weighted combination of a likelihood gradient and an adversarial gradient by adopting an adversarial training mechanism in which adversarial items are introduced; and using the trained model to generate digital twin data through Gibbs sampling based on a given condition input variable. According to the method, heterogeneous data can be directly processed, the original statistical characteristics of the data are reserved, and the precision of model parameter estimation and the fidelity of generated data are improved.

The invention discloses a partial discharge fault diagnosis method and system based on deep confidence, and aims to improve the precision of partial discharge fault diagnosis of power equipment. According to the method, an original binary partial discharge time sequence PRPS signal is read, an effective section is intercepted, amplitude transformation is carried out, and a de-duplicated and normalized fault diagnosis data set is constructed; a multi-layer convolution restricted Boltzmann machine structure is adopted, and an unsupervised contrast divergence algorithm is combined for layer-by-layer pre-training, so that automatic extraction of deep time sequence features of the partial discharge signals is realized; further stacking to form a convolutional deep belief network, connecting a classifier, and performing supervised fine tuning training on the network by using a cross entropy loss function with category weight; in the reasoning stage, normalization processing is carried out on a signal to be diagnosed, features are extracted through the pre-training network, and finally a predicted fault category is output according to the classifier.

The application discloses a multi-modal critical edge biomarker identification method, takes an individual cancer patient as a dynamic network system, combines a dynamic network theory biomarker theory and a multi-modal evolutionary algorithm, performs hidden space search by using a restricted Boltzmann machine on the basis of an MMPDNB model, and is a new multi-modal PDENB identification model. Firstly, a PEN of the cancer individual patient is constructed. Then, an optimization objective function is designed. Finally, a multi-modal optimization algorithm is used to search for a PDENB set. The application can not only promote the researches on a mathematical model and an algorithm design of the PDENB identification problem, but also help to understand the individual heterogeneity of the cancer, and realize the early diagnosis and treatment of the cancer individual patient.

The invention provides a transformer capacitance compensation through-current method and system based on deep learning, and relates to the technical field of reactive power compensation of a power system. The method comprises the following steps: acquiring a transformer signal to obtain standardized input data; modeling of the double-layer restricted Boltzmann machine is completed; generating a deep hidden feature vector; generating a capacitor switching parameter; the control hardware module receives a control instruction and triggers a relay to act; and comparing the reconstruction error with a preset threshold value, maintaining the current switching state when the reconstruction error does not exceed the threshold value, and regenerating and adjusting the capacitor switching parameter when the reconstruction error exceeds the threshold value. According to the method, a complete process from standardized input, feature modeling and capacitance parameter mapping to control execution and error closed-loop updating is constructed, adaptive adjustment of capacitance switching action and whole-process data retention are supported, and decision consistency and execution stability under complex working conditions are improved.

The invention provides a twin self-calibration photoelectric probability bit circuit unit and a preparation and use method thereof, the circuit unit comprises a self-calibration photoelectric differential module, a voltage comparator and a reference voltage source, the self-calibration photoelectric differential module is a pair of photoelectric indium gallium zinc oxide (IGZO) thin film transistors which are tightly coupled in space; the device is patterned through an ultraviolet lithography process and a radio frequency magnetron sputtering process at the same time, atomic-scale matching of a reference tube and a photosensitive tube in geometric dimension, film thickness and interface state density is ensured, differences only exist in illumination conditions, common-mode interferences such as aging caused by temperature drift and bias stress are offset by effectively utilizing a difference principle, and the performance of the device is improved. The physical characteristic of highly consistent aging trend is utilized to construct a synchronous drifting series voltage division network, and high-precision and high-stability in-situ photoelectric probability calculation is realized; probability bits are generated through dual modulation of grid voltage and light intensity, and the method is suitable for Bayesian reasoning, restricted Boltzmann machines and other probabilistic neural network hardware.

The invention discloses a fuze falling angle identification method based on bispectrum analysis and a deep belief network. The method comprises the following steps: S1, preprocessing a received fuze echo signal; s2, calculating a third-order cumulant of the preprocessed echo signal by applying an axial integral bispectrum method to obtain a bispectrum feature; s3, selecting and amplifying the integral bispectrum features by using a one-dimensional Fisher class separation degree to form feature vectors; s4, constructing a deep belief network model composed of two layers of restricted Boltzmann machines and a layer of back propagation neural network; and S5, inputting the bispectrum analysis features into a deep belief network, and completing accurate identification of the fuse falling angle. According to the method, the advantages of bispectrum analysis and the deep belief network are combined, so that efficient and accurate identification of the fuse falling angle is realized.

Reinforcement learning with space state pruning is disclosed. States of an environment used in training a reinforcement learning model are pruned using a restricted Boltzmann Machine. Reducing the number of states, by pruning, reduces time to convergence.